nmz0429 / biwako Goto Github PK
View Code? Open in Web Editor NEWThe largest freshwater lake. The home of onnx models.
License: GNU General Public License v3.0
The largest freshwater lake. The home of onnx models.
License: GNU General Public License v3.0
It seems to be useful for user if the model can find pre-downloaded file not not only on current directory but also other places such as caches.
E.g. links, documents...
Add FastAPI pre-defined code in api module.
Sample minimum implementation of how to use this repository with FastAPI for web application.
Will be added.
Rather than conda environment, add docker image file.
What?
Any?
Enable all dead CIs
Hassle
Update dependencies
N/A
setup.py
lacks some dependent modules.
Update setup.py
to latest version.
Any?
Old yolo implementation requires torch.
Avoid the dependence of torch.
Any?
Bump up the version of Mkdocs and purge outdated extensions
N/A
README is not ready for publishment
Update README
Any?
Add some higher level API for video
With this, user can
Any?
The API calls render()
without some optional arguments.
Any?
**kwargs
to render method of all classesAdd sample output/video for demo purpose
What?
Probably one image per model and some videos for selected models
Any?
demo
folderThe current implementation uses fixed positions for writing text on the image. Add user configurability for that.
Tqdm for weight download is not animated properly.
The progress bar for weight download is not properly updated while download is in place.
Sample implementation.
https://blog.narito.ninja/detail/66
Add lightweight object detector NanoDet
Implement NanoDet onnx module
Publish Documentation by Github Pages
Publish documentation which satisfies
MkDocs/gh actions
Add option to measure runtime of inference
For predict()
and possibly render()
add ability to measure runtime theirselves.
Since it is likely too exhaustive to modify all such methods, add new method or attribute to base class.
Any?
Current logic only looks for the cwd and auto download it to there if not found.
Add Object Tracking post processor for object detection module.
See ~/github/onnx_byte
for current progress
Add Edge Detection Model
Add some edge detection model and its visualization code.
Any?
Current implementation uses PyTorch for NMS. Remove this dependence by replacing corresponding lines to cv2.dnn.nms
Add some way for user to see which models (and weight types) are available.
Something like
BiWAKO.YOLO.print_weights()
E.g. links, documents...
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.